Journal of Theory and Practice of Engineering Science 2024

4 papers
The 2024 edition of the Journal of Theory and Practice of Engineering Science featured research focused on the application of machine learning and deep learning architectures across diverse sectors. Key themes included natural language processing for sentiment analysis and e-commerce optimization, alongside predictive modeling in marketing. Methodologies highlighted in this year's publications involved hybrid models such as CNN-LSTM for analyzing political discourse and BERT-based frameworks for processing consumer feedback to improve recommendation systems. Research also extended into computer vision and biological engineering, specifically regarding high-precision neuronal segmentation using ensemble techniques like YOLOX, Mask R-CNN, and UPerNet. Other studies addressed business analytics through AI-driven customer churn prediction. Prolific contributors to this volume included researchers such as Chufeng Jiang, Jize Xiong, Mingyang Feng, and Ning Zhang. Collectively, the 2024 papers reflect a trend toward integrating complex neural network ensembles to solve practical problems in social science, commerce, and medical imaging.

Top Authors

AuthorPapers
Ang Li1

Papers

Title
Dose My Opinion Count? A CNN-LSTM Approach for Sentiment Analysis of Indian General Elections
Enhancing E-commerce Recommendations: Unveiling Insights from Customer Reviews with BERTFusionDNN
High-Precision Neuronal Segmentation: An Ensemble of YOLOX, Mask R-CNN, and UPerNet
Utilizing Data Science and AI for Customer Churn Prediction in Marketing